Multi-Oriented Text Detection with Fully Convolutional Networks

Abstract

In this paper, we propose a novel approach for text detec- tion in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine pro- cedure. First, a Fully Convolutional Network (FCN) model is trained to predict the salient map of text regions in a holistic manner. Then, text line hypotheses are estimated by combining the salient map and character components. Fi- nally, another FCN classifier is used to predict the centroid of each character, in order to remove the false hypotheses. The framework is general for handling text in multiple ori- entations, languages and fonts. The proposed method con- sistently achieves the state-of-the-art performance on three text detection benchmarks: MSRA-TD500, ICDAR2015 and ICDAR2013.

Accepted by CVPR2016

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Fully Convolutional Networks for Semantic Segmentation
• Robust Text Detection in Natural Scene Images
• Holistically-Nested Edge Detection

Cited by in corpus (34)

• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• EAST: An Efficient and Accurate Scene Text Detector
• Robust Scene Text Recognition with Automatic Rectification
• Single Shot Text Detector with Regional Attention
• Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
• Deep Direct Regression for Multi-Oriented Scene Text Detection
• PixelLink: Detecting Scene Text via Instance Segmentation
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
• Multi-Oriented Text Detection and Verification in Video Frames and Scene Images
• WordSup: Exploiting Word Annotations for Character based Text Detection
• Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation
• Fused Text Segmentation Networks for Multi-oriented Scene Text Detection
• A pooling based scene text proposal technique for scene text reading in the wild
• Scene Text Detection with Supervised Pyramid Context Network
• Rotation-Sensitive Regression for Oriented Scene Text Detection
• WeText: Scene Text Detection under Weak Supervision
• Feature Enhancement Network: A Refined Scene Text Detector
• Detecting Oriented Text in Natural Images by Linking Segments
• Verisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
• WordFence: Text Detection in Natural Images with Border Awareness
• Deep Scene Text Detection with Connected Component Proposals
• Learning to detect and localize many objects from few examples
• ArbiText: Arbitrary-Oriented Text Detection in Unconstrained Scene
• DeRPN: Taking a further step toward more general object detection
• Primitive Representation Learning for Scene Text Recognition
• AON: Towards Arbitrarily-Oriented Text Recognition
• An End-to-end Video Text Detector with Online Tracking
• On Study of the Reliable Fully Convolutional Networks with Tree Arranged Outputs (TAO-FCN) for Handwritten String Recognition
• TextTubes for Detecting Curved Text in the Wild
• Correlation Propagation Networks for Scene Text Detection
• A Machine Learning Framework for Data Ingestion in Document Images
• Accurate Scene Text Detection through Border Semantics Awareness and Bootstrapping
• A DNN Framework For Text Image Rectification From Planar Transformations
• TextContourNet: a Flexible and Effective Framework for Improving Scene Text Detection Architecture with a Multi-task Cascade